多元经验模态分解及在SAR图像目标识别中的应用

提出基于多元模态分解的合成孔径雷达（SAR）目标识别方法。多元模态分解是传统模态分解的多元扩展,能够有效避免传统算法中的模态混叠问题。采用多元模态分解对SAR图像进行处理,获得的多层次固有模式函数（IMF）能够更为有效地反映目标的时频特性。不同IMF之间具有良好互补性,同时它们描述同一目标因而具有内在关联性。分类阶段,采用联合稀疏表示对分解得到的IMF进行表征。联合稀疏表示在多任务学习的理念下,对多个关联稀疏表示问题进行求解,可获得更为可靠的估计结果。在获得各层次IMF对应的稀疏表示系数矢量的基础上,计算不同类别对于当前测试样本多层次IMF的重构误差之和,进而判定测试样本的目标类别。基于MSTAR数据集开展实验,通过在标准操作条件、俯仰角差异、噪声干扰以及目标遮挡条件下进行对比分析,验证了提出方法的有效性。     

基于二维经验模态分解的高光谱影像去噪方法

高光谱遥感图像同时具有二维空间信息数据和一维光谱信息数据,具有图谱合一的特点且谱间信息具有强烈的相关性,针对高光谱图像的这些特点,提出一种基于二维经验模态分解的高光谱图像降噪方法。该方法利用二维经验模态分解对各波段的高光谱图像分别进行分解,得到不同尺度的固有模态函数;根据含噪声较大的波段和含噪声较小的波段的谱间对应关系计算权系数值,对含噪声较小波段的高频固有模态函数系数进行加权求和,利用加权后的系数值代替含噪声较大的波段的高频固有模态函数系数;利用去噪后的高频系数进行重构得到去噪后的高光谱图像。实验表明,该方法能够对高光谱影像进行有效去噪,同时亦能较好地保留图像细节信息,与经典的小波去噪方法相比,使用该方法去噪后的图像具有更高的峰值信噪比和更好的视觉效果。     

基于窗口经验模式分解的医学图像增强

提出了基于窗口经验模式分解(WEMD)的医学图像增强算法。用WEMD算法分解医学图像,能够自适应地提取图像的内涵模式函数(IMF)分量。利用IMF分量图像的直方图服从正态分布的特性,结合直方图匹配算法的增强能力处理前几个IMF分量,经处理的IMF分量中的高频细节信息得到增强。将处理后的IMF分量和剩余分量重构,获取增强的医学图像。实验表明,WEMD算法增强效果优于目前的图像增强算法。     

基于偏微分方程的遥感图像目标提取

从遥感图像中提取感兴趣的目标是遥感和地学领域的一个重要任务.先前的研究主要集中于目标提取的精度,而很少关注目标提取的效率.因此,作者提出一个基于偏微分方程的框架来进行半自动多类目标提取.首先,作者对水平集方法,非线性扩散,以及活动轮廓之间的数学关系进行了深入的探究.从探究的结果作者发现基于边缘和基于区域的偏微分方程在目标提取中同等重要,因此作者把它们概括成一个统一的框架.接着,为了使计算更加高效,作者用尺度空间滤波替换传统的曲率归一项.最后,作者通过一系列实验证明了该方法的有效性.     

Robust image watermarking based on multiband wavelets and empirical mode decomposition.

In this paper, we propose a blind image watermarking algorithm based on the multiband wavelet transformation and the empirical mode decomposition. Unlike the watermark algorithms based on the traditional two-band wavelet transform, where the watermark bits are embedded directly on the wavelet coefficients, in the proposed scheme, we embed the watermark bits in the mean trend of some middle-frequency subimages in the wavelet domain. We further select appropriate dilation factor and filters in the multiband wavelet transform to achieve better performance in terms of perceptually invisibility and the robustness of the watermark. The experimental results show that the proposed blind watermarking scheme is robust against JPEG compression, Gaussian noise, salt and pepper noise, median filtering, and ConvFilter attacks. The comparison analysis demonstrate that our scheme has better performance than the watermarking schemes reported recently.     

基于经验模态分解的本征熵及其应用研究

以经验模态分解和信息熵理论为基础,可以提出本征熵这一新指标,用于大型设备运行稳定性定量监测。通过在十余家大型企业的实际应用和对应实验表明,本征熵较好地反映了设备运行时不同本征模态的稳定性,为设备的状态监测和诊断提供了运行稳定性的量化数据。     

Multivariate empirical mode decomposition and application to multichannel filtering

Empirical Mode Decomposition (EMD) is an emerging topic in signal processing research, applied in various practical fields due in particular to its data-driven filter bank properties. In this paper, a novel EMD approach called X-EMD (eXtended-EMD) is proposed, which allows for a straightforward decomposition of mono- and multivariate signals without any change in the core of the algorithm. Qualitative results illustrate the good behavior of the proposed algorithm whatever the signal dimension is. Moreover, a comparative study of X-EMD with classical mono- and multivariate methods is presented and shows its competitiveness. Besides, we show that X-EMD extends the filter bank properties enjoyed by monovariate EMD to the case of multivariate EMD. Finally, a practical application on multichannel sleep recording is presented.     

极点均值型经验模式分解及其去噪应用

使用经验模式分解（EMD）对信号进行去噪时,由于EMD 本身会产生模态混叠,往往很难将噪声完全分离。针对这一问题,提出了一种新型的极点均值型EMD 方法,并且给予固有模态函数（IMF）一个新的定义。首先,将相邻极点平均以求得均值包络,然后迭代相减进而获得IMF。最后用原始信号减去分离出的高频IMF 实现去噪。随机信号仿真以及激光雷达回波信号去噪实验表明,该方法与EMD 分解相比,可以更好地将噪声分离,有效地抑制模态混叠,更可以极大地减小均方误差。因此,极点均值型EMD 拥有很好前景。     

Reduced reference image quality assessment based on statistics in empirical mode decomposition domain

This paper deals with the image quality assessment (IQA) task using a natural image statistics approach. A reduced reference (RRIQA) measure based on the bidimensional empirical mode decomposition is introduced. First, we decompose both, reference and distorted images, into intrinsic mode functions (IMF) and then we use the generalized Gaussian density (GGD) to model IMF coefficients of the reference image. Finally, we measure the impairment of a distorted image by fitting error between the IMF coefficients histogram of the distorted image and the estimated IMF coefficients distribution of the reference image, using the Kullback–Leibler divergence (KLD). Furthermore, to predict the quality, we propose a new support vector machine-based (SVM) classification approach as an alternative to logistic function-based regression. In order to validate the proposed measure, three benchmark datasets are involved in our experiments. Results demonstrate that the proposed metric compare favorably with alternative solutions for a wide range of degradation encountered in practical situations.     

Hierarchical decomposition based on a variation of empirical mode decomposition

Adaptive methods of signal analysis have proved a very useful tool for analysis of non-stationary signals. This is due to the ability of these methods to adapt to the local structures of the signals being analysed, as these methods are not constrained by a fixed basis. Empirical mode decomposition (EMD) is among the more recent data-adaptive signal decomposition methods, which decomposes a given signal into modes which are hierarchically arranged based on their frequency content. In this paper, we will present a novel adaptive hierarchical decomposition scheme based on a novel modification of EMD, namely empirical mode decomposition-modified peak selection (EMD-MPS). EMD-MPS allows a time-scale-based signal decomposition, thereby allowing control over the decomposition process, not possible in the original EMD algorithm. Using time-scale-based decomposition and the properties of EMD-MPS, a given signal can be decomposed into octave frequency bands, with the centre frequency of the separated modes given by the frequency separation criterion of EMD-MPS. The spectral limits of the separated bands are established, and their relation with the centre frequency derived empirically. The method is validated by its application to simulated and real signals.     

Automatic analysis of human posture equilibrium using empirical mode decomposition

The present study proposes a new approach for the assessment of the human balance control. This approach is based on the decomposition of the center of pressure displacement using empirical mode decomposition (EMD) that provides an effective time-frequency analysis of non-stationary signals. Twenty-eight healthy subjects performed quiet standing in four conditions—feet apart/together with respect to eyes open/closed—while recording the stabilometric signals in the anteroposterior (AP) and mediolateral (ML) directions. The EMD method decomposes each stabilometric signal into several subsignals called intrinsic mode functions (IMFs). Stabilogram-diffusion analysis technique is applied to generate the diffusion curve of each IMF signal. Each diffusion curve is modeled as a second-order system and provides representative features, such as the gain parameter. Analysis of the gain parameter shows the major effect of visual input and feet conditions on the strategy to control/stabilize the balance. Significant differences were found between young and elderly, and between women and men. In addition, the impact of feet position seems to be higher in ML direction than in AP direction.     

The complex bidimensional empirical mode decomposition

A new method for computing complex bidimensional empirical mode decomposition (BEMD) is presented in this paper. The proposed complex-BEMD uses four quadrant spectra to apply standard BEMD to four real-valued 2D signals. The so-generated intrinsic mode functions (IMFs) are 2D complex-valued, which facilitates the extension of the standard BEMD to the complex domain. The proposed complex-BEMD can be successful for the analysis of real-world 2D complex-valued signals, such as 2D NMR signals. Moreover, the proposed complex-BEMD can be applied for color image processing. A simple color image fusion algorithm based upon the proposed complex-BEMD has also been developed to have the exhibition of the potential. By our proposed complex-BEMD and image fusion algorithm, the well-fused results can be obtained, if the mode mixing in BEMD is alleviated.     

基于经验模态分解提取纹理的图像融合算法

为了提升医学图像融合质量,采用了一种基于2维经验模态分解（BEMD）特征分类和复合型脉冲耦合神经网络的医学图像融合算法。首先将多模医学图像经过BEMD分解成2维内蕴模函数（BIMF）和残差项,然后分别将BIMF层和残差项值输入脉冲耦合神经网络（PCNN）中,得到各自的点火映射图,再将相同点火次数的像素提取归类,点火次数大的对应图像纹理,归为纹理类,其余归为背景类;统计各个纹理类集合中的像素极值确定灰度分布范围,最后将两幅图像中纹理类像素集合处于灰度分布范围的像素通过PCNN进行融合,其它像素通过双通道PCNN进行融合。结果表明,该算法解决了PCNN对偏暗图像的处理效果不理想的问题,与传统融合算法相比,性能具有优势,且能够较大幅度提高融合图像的质量。     

基于经验模态分解的激光陀螺随机信号消噪

各种随机噪声是导致激光陀螺产生误差的主要因素,且其性质特殊,很难用传统的滤波方法去除。为了抑制激光陀螺的随机漂移,提高使用精度,提出了一种新型经验模态分解方法对陀螺随机漂移测试信号进行滤波处理。该方法将经验模态分解的内模函数中两个相邻过零点之间的信号定义为模态单元,并作为基本分析对象,通过对模态单元振幅的阈值处理来判断模态单元的类型,进而建立模态单元滤波模型。分析了经验模态分解法在分解不同Hurst指数分形高斯噪声时模态振幅的演化规律,并建立了一种用于高斯消噪的阈值选取规则。运用该方法对激光陀螺测试数据进行了滤波降噪实验,并用Allan方差法对不同降噪算法的降噪效果进行了比较分析,实验结果验证了该方法的有效性和优越性。     

基于二维经验模态分解的三维面形测量

采用结构光投影的三维面形测量,为了得到包含待 测物体高度信息的基频成分,变形条纹图中通常含有随机噪声和背景信息需要去除。提出一 种基于二维经验模态分解(2D-EMD)的三维面形测量方法。2D-EMD用于去除低频背景分量 并抑制噪声影响,再结合二维希尔伯特变换提取三维面形的相位信息,最后根据相位与高度 的映射关系得到被测物体的三维形貌。2D-EMD采用完全的二维分析方法,考虑了条纹图行 与行之间的相关性,能有效提取任意方向条 纹图中的调制相位。由于不需要像聚合EMD(EEMD)反复添加噪声再分解的去噪过程,缩短了 数据的处理时间。计算机仿真结果表明,与傅里叶变换轮廓术(FTP)相比,较大陡跳误差从 －40mm降到了－1～1mm。实验结果也证明了 本文方法的有效性。     

基于经验模态分解与回归分析的空间外差光谱目标提取

为识别空间外差光谱仪探测目标干涉信号的特征信息,提出一种基于经验模态分解与回归分析的空间干涉谱目标提取方法。首先对预处理后的光谱进行经验模态自适应分解,得到各阶次固有模态分量并分别计算它们与原始光谱信号的Pearson相关系数,根据相关系数分选准则判定背景与目标信息重构的分界点。然后计算重构背景与实测背景间的Pearson相关系数来判定经验模态分解结果。对信号主导的固有模态分量利用小波软阈值进行消噪,重构较纯净的目标特征信息;利用目标特征信息与原始干涉光谱信息进行多元线性回归分析获得最佳的近似滤波系数,构造滤波器并应用到目标信号,提取目标。最后通过差谱信号与提取的目标光谱的Pearson相关系数来判别提取的目标信号。实验结果表明:经验模态分解可将背景与目标近似分离;在未知背景信号情况下,利用经验模态分解与回归分析可实现钾共振双线特征光谱的提取。     

一种改进的基于EMD分解的超宽带信号消噪算法

针对低信噪比超宽带信号的消噪问题,提出一种改进的基于经验模式分解(EMD)的消噪算法.该算法首先对含噪信号进行EMD分解,得到多个固有模态函数(IMF)分量,然后选取高阶IMF重构原信号,达到消噪的目的.针对对UWB信号的IMF重构过程中阶数阈值难以确定的问题,通过数值仿真的方法,得到信号分量和噪声分量在不同阶IMF上的能量分布特性;在对所得特性进行分析的基础上,设计了一种数据自适应的阶数阈值选取算法,解决了EMD消噪中的阶数阈值选取问题.仿真结果表明,EMD消噪算法能够在较低信噪比下提供平均10 dB的信噪比增益,可以有效地对超宽带信号进行消噪.     

基于经验模式分解的Wigner-Ville分布交叉项抑制方法

时频分析作为时变非平稳信号分析的有力工具,成为现代信号处理研究的一个热点.这种分析方法提供了时间域与频率域的联合分布信息,为我们清楚地描述了信号随时间变化的关系.Wigner-Ville分布由于其良好时频集聚性,在非平稳信号分析中得到广泛应用,本文针对Wigner-Ville分布中的交叉项问题,提出了基于经验模式分解的Wigner-Ville分布,即对多分量信号运用经验模式分解,将其分解为单分量信号,再对每个单分量信号求Wigner-Ville分布进行线性叠加.提出运用相关系数法对经验模式分解伪分量进行剔除,提高了该方法的精度,并将该方法与Cohen类方法进行比较,阐述了该方法的优点.     

Method for eliminating mode mixing of empirical mode decomposition based on the revised blind source separation

Since mode mixing of empirical mode decomposition (EMD) is mainly caused by the intermittence and noise, we propose a novel method to eliminate mode mixing of EMD based on the revised blind source separation. To this aim, an optimal morphological filter is employed to eliminate the noise. As a result, the component of mode mixing caused by noise is suppressed. Furthermore, the de-noised signal is decomposed into different intrinsic mode function (IMF) components through the EMD algorithm. Since it is impossible to apply blind source separation to a single channel signal directly, the IMF component, which has mode mixing is chosen and reconstructed in the phase space. Following that, the equivalent hypothetical signals are obtained. Finally, an improved fixed-point algorithm based on independent component analysis (ICA) is introduced to separate the overlapping components. The analysis of simulation and practical application demonstrates that our proposed method can effectively tackle the mode mixing problem of EMD.     

A 3-D integral equation-based approach to the analysis of real-lifeMMICs application to microelectromechanical systems

In this paper, we introduce a three-dimensional method-of-moments approach, suitable for the analysis of real-life monolithic circuits for microwave/millimeter waves. It shares the flexibility and the efficiency of the currently available spectral-domain commercial simulators, while allowing all metallizations to have finite thickness and finite conductivity and the ability to handle dielectric discontinuities. The method is successfully applied to several structures, like metal-insulator-metal capacitor, spiral inductors, and microelectromechanical capacitive switches in the 1-50-GHz frequency range